naip
Datasets
All datasets matching “naip”s2-naipAI2-S2-NAIP is a remote sensing dataset consisting of aligned NAIP, Sentinel-2, Sentinel-1, and Landsat images spanning the entire continental US.
Data is divided into tiles.
Each tile spans 512x512 pixels at 1.25 m/pixel in one of the 10 UTM projections covering the continental US.
At each tile, the following data is available:
National Agriculture Imagery Program (NAIP): an image from 2019-2021 at 1.25 m/pixel (512x512).
Sentinel-2 (L1C): between 16 and 32 images captured within a few… See the full description on the dataset page: https://huggingface.co/datasets/allenai/s2-naip.ZoomLDM-demo-dataset-NAIPDemo dataset for our CVPR 2025 paper "ZoomLDM: Latent Diffusion Model for multi-scale image generation". We extract patches from the Chesapeake land cover dataset.
Usage
from datasets import load_dataset
ds = load_dataset("StonyBrook-CVLab/ZoomLDM-demo-dataset-NAIP", name="3x", trust_remote_code=True, split='train')
print(np.array(ds[0]['ssl_feat']).shape)
>>> (1024, 4, 4)
Citations
@inproceedings{yellapragada2025zoomldm,
title={ZoomLDM: Latent Diffusion Model for… See the full description on the dataset page: https://huggingface.co/datasets/StonyBrook-CVLab/ZoomLDM-demo-dataset-NAIP.hyperscale-datacenter-segmentation-naip
Hyperscale Data Center Segmentation (NAIP)
Hand-digitized training data for detecting hyperscale data center
footprints in aerial imagery, with a trained baseline model.
Contents
path
what it is
datacenters.geojson
190 hand-digitized data center footprint polygons (QGIS; named facilities, e.g. vantage_0)
chips/
757 NAIP aerial chips, 256×256 px, 4-band RGBN, 0.6 m resolution (GeoTIFF, georeferenced) — labeled facilities plus surrounding negatives… See the full description on the dataset page: https://huggingface.co/datasets/rbhughes/hyperscale-datacenter-segmentation-naip.naip-16d-city-cubes
NAIP 16-Day City Cubes (materialized tiles)
Each row is a 512×512 chip with 16 layers (composites, single-band indices, and masks).
What’s included (no pseudoRGB)
RGB composites: naip_rgb, s2_rgb, dem_rgb
Mono S2 layers (published as single-channel images): s2_B08, s2_MSAVI, s2_NDVI, s2_NDWI, s2_SCL
Other monos: naip_ndvi
Semantic masks: labels (task labels), landfire_family, cdl
Metadata: tile_id, city, bbox (west,south,east,north), chip_px, split, meta_json
Note:… See the full description on the dataset page: https://huggingface.co/datasets/gdurkin/naip-16d-city-cubes.NAIPL8-S2-NAIP
L8-S2-NAIP Cross-Sensor Reconstruction Dataset
This repository contains the L8-S2-NAIP dataset, a unified triple-sensor remote sensing benchmark for cross-sensor reconstruction of Landsat-8 imagery from 30m to 2.5m spatial resolution.
📥 Data Source
All raw images are exported from Google Earth Engine (GEE) platform in GeoTIFF format. The dataset covers 22 geographically diverse regions across the contiguous United States.
File Naming Convention… See the full description on the dataset page: https://huggingface.co/datasets/namelesscoder/L8-S2-NAIP.